Unlock instant, AI-driven research and patent intelligence for your innovation.

Feature extraction and identification method for load category of distribution network

A technology of feature extraction and identification method, which is applied in the direction of electrical components, circuit devices, AC network circuits, etc., and can solve problems such as inability to deeply analyze the duration and power consumption of power users

Active Publication Date: 2019-12-13
BEIFANG UNIV OF NATITIES
View PDF7 Cites 4 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0002] At present, the energy meter used for electric energy metering of electric power users can only record the power consumption parameters such as the user's peak, flat and valley power, maximum demand, etc., and cannot deeply analyze the specific load of the power user, its duration, power consumption and other information

Method used

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • Feature extraction and identification method for load category of distribution network
  • Feature extraction and identification method for load category of distribution network
  • Feature extraction and identification method for load category of distribution network

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0067] The present invention will be described in detail below in conjunction with the accompanying drawings and specific embodiments.

[0068] The present invention is a feature extraction and identification method for distribution network load category, such as figure 1 As shown, the specific steps are as follows:

[0069] Step 1. Sampling the voltage and current of the load in the distribution network to obtain the sampled voltage and current of the load:

[0070] The voltage and current u(i) of the sampled load s.α for

[0071]

[0072] In formula (1), u s.α (t) represents the sampling voltage of the load, U s Indicates the maximum amplitude of the load voltage, ω 1 Indicates the power frequency fundamental voltage current angular frequency, i s.α (t) represents the sampling current of the load, I s.dc means i s.α The magnitude of the DC component in (t); I s.h Indicates the current i with frequency h s.h The maximum magnitude of (t), h is a natural number oth...

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

PUM

No PUM Login to View More

Abstract

The invention discloses a feature extraction and identification method for the load category of a distribution network. The method specifically comprises the steps that the voltage and current of an electrical load of the distribution network are sampled; phase-locking is carried out on the sampled load voltage, and the sampled voltage and current are transformed to acquire the fundamental activecomponent, fundamental reactive component, direct current component and h-th harmonic component in the load current; the eigenvector of load state identification is calculated; the characteristic value to be identified of the load is calculated; and matching operation is carried out on the characteristic value to be identified and characteristics in a load state reference library to identify unknown load types and output the load category. According to the invention, different weighting factors are assigned to different identification characteristic parameters, which improves the load identification rate; in addition, the misjudgment of the load identification category is eliminated; and accurate start and end times are provided for classified measurement of the power consumption of different loads.

Description

technical field [0001] The invention belongs to the technical field of instruments and meters, and relates to a feature extraction and identification method for distribution network load categories. Background technique [0002] At present, the energy meter used for electric energy metering of electric power users can only record the power consumption parameters such as peak and valley power consumption and maximum demand, but cannot deeply analyze the specific load of power users, its duration, power consumption and other information. Since different loads have different working characteristics, the power and current they draw from the distribution network contain their own unique information. Non-intrusive Load Monitoring (NILM) technology extracts the characteristics of the load by analyzing the voltage and current of the power user's load, and the NILM system analyzes the power consumption information of different loads based on these characteristics, and finally obtains...

Claims

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

Application Information

Patent Timeline
no application Login to View More
IPC IPC(8): H02J3/00
CPCH02J3/00
Inventor 张新闻张若源李建炜
Owner BEIFANG UNIV OF NATITIES